© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8025
    Prev
    Next
    INDEX
    Explanations

    code snippets with directory names and internet addresses

    oai_token-act-pair · gemini-2.0-flash

    dir

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -1.50
     auffi
    -1.26
     myſelf
    -1.16
    ^(@)
    -1.12
     Efq
    -1.12
     reaſon
    -1.11
     vectorielle
    -1.11
     raiſ
    -1.09
     faſt
    -1.09
     Monfieur
    -1.09
    POSITIVE LOGITS
     N
    0.63
     
    0.62
     B
    0.60
     (
    0.58
     R
    0.57
     As
    0.57
     For
    0.57
     P
    0.57
      
    0.57
     D
    0.54
    Activations Density 0.514%

    No Known Activations